Estimation of Mobile Vehicle Range & Position Using The Tobit Kalman Filter

Censored measurements arise frequently in engineering applications in the form of saturation, limit of detection, and occlusion effects. Censored data regression uses a formulation known as the Tobit model. We have recently presented a novel extension of the Kalman filter that allows for optimal state tracking in the presence of censored measurements. We call this formulation the Tobit Kalman filter. In this paper, we present an application of the Tobit Kalman filter to mobile vehicle position estimation using received signal strength from a number of antennas. Received signal strength drops below the noise floor as distance increases, and is therefore a censored measurement. We will briefly introduce the Tobit Kalman filter and compare its performance on the position estimation problem with the standard Kalman filter. Stable closed-loop control will be demonstrated by use of the Tobit Kalman filter as an observer in a linear-quadratic-Gaussian regulator.